JPS62281089A - Recognition method for pattern information - Google Patents

Abstract

PURPOSE:To correctly recognize a pattern in an extremely short time by detecting the histogram of a stroke distribution every area obtained by dividing pattern information and recognizing the number of the maximum generations of the histogram as the central value of the divided areas. CONSTITUTION:A CPU 50 takes the histogram of the number of the strokes in a lateral direction and a vertical direction respectively every line, stores in the line histogram buffer 22 of a RAM 57 and then divides the reading pattern into respective prescribed areas. Subsequently, the minimum value of the pattern every line in the previously obtained prescribed area is obtained and stored in an area histogram buffer 23 as the central value. Similarly, the number of the most frequency generating strokes of the histogram distribution every line in the previously obtained prescribed areas and stored in the area histogram buffer 23. Then, the central value every area is obtained and stored in a reading pattern 24. In the areas 1-6, the minimum value of the histogram distribution is defined to be the central value and in the areas A-D, the number of the most frequency generating strokes is defined to be the central value.

Description

Detailed Description of the Invention 3. Detailed Description of the Invention [Field of Industrial Application] The present invention relates to a pattern information recognition method for automatically reading and recognizing unknown characters such as alphabets and numbers.

[Prior Art] FIG. 10 shows character recognition processing of a conventional character recognition device of this type.

The characters on the manuscript paper P are read character by character as shown in step s81 and photoelectrically converted, and this is further converted in step S82.
It is converted into a binary data pattern of "1°" and "0°". In the following step S83, pre-processing is performed to make the processing to be described later effective, that is, noise processing such as black dots on the paper P on which characters are recorded based on the binarized pattern in step S82, and character/figure boundaries are performed. A series of processing is performed, including surface smoothing. Next, in step S84, feature extraction processing is performed to extract several features (intersections, branch points, number of loops, stroke length information, etc.) necessary for character recognition. Depending on this extraction result, some characters with common features are selected from a large number of characters.

Next, in step 585 and subsequent steps, dictionary collation processing and recognition processing are performed as identification processing for selecting a unique character from among the characters.

First, it is checked whether dictionary guidance (search) is possible according to the features extracted in step S85. If the feature extracted here is not worthy of guiding a dictionary, the process advances to step 388, and unrecognizable is output. On the other hand, if dictionary guidance is possible based on the extracted feature points, step S8
In step 6, the prepared dictionary is searched and sequentially compared with the previously extracted features. If a match is found as a result of the comparison in step S87, the matching result is outputted as a recognition output in step 38B. If a match cannot be found, it is output as unrecognizable.

[Problems to be solved by the invention] However, according to this conventional recognition method, simple characters (
The above-mentioned complicated processing is performed even for characters that are easily recognized (characters that are easy to recognize), alphabets, numbers, etc., which has the disadvantage that it takes too much processing time.

Further, the configuration for realizing the above processing is also complicated, and there are various problems in terms of increased cost and reliability.

[Means for solving the problems] The present invention has been made in view of the problems of the prior art described above, and includes the following configuration as a means for solving the problems described above.

That is, a reading means for optically reading the pattern information on the reading surface, an area dividing means for dividing the pattern information read by the means into predetermined areas, and a stroke for each area divided by the area dividing means. Consisting of a detection means for detecting a histogram of the distribution, and a recognition means for recognizing read pattern information from the histogram of the stroke distribution detected by the one detection means [Operation] In the above configuration, the pattern information read by the reading means is divided by means for dividing the pattern information read by the reading means. The detection means detects the histogram of the stroke distribution within a certain range for each region divided by the dividing means, and the recognition means detects the maximum of the histogram of the stroke distribution detected by the detection means. The number of occurrences is recognized as the representative value of the divided area.

[Example] Hereinafter, an example according to the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram of one embodiment of the present invention.
2 is an optical disk that stores the image information read by the reader 1; 3 is a host computer that controls the entire embodiment; 4 is a keyboard; 5 is a A CRT displays image information, operation information, etc., and 6 is a printer that prints out the image information. Further, reference numeral 7 denotes an auto feeder that automatically feeds originals one by one to the original reading surface of the reader 1.

In the host computer 3, 50 is a CPU that controls the entire apparatus according to the control program shown in FIG. 4 stored in the ROM 51. The CPU 50 is preferably configured with a microcomputer MC68000 manufactured by Motorola, for example. 51 is a ROM, ROM5
1 includes a standard feature pattern storage area 51a. 5
2 is a CRT interface that controls the interface with the CRT 5; 53 is a keyboard interface that controls the interface with the keyboard 4; and 54 is an optical disk interface that controls the interface with the optical disk. Further, 55 is a reader interface that controls the interface with the reader 1, 56 is a printer interface that controls the interface with the printer 6, and 57 is an R that stores the processing progress, the reading mark recognition processing progress, etc.
AM, 60 is a bus that connects each component.

A detailed storage area of the RAM 57 is shown in FIG.

In FIG. 2, 21 is a pattern buffer, 22 is a line histogram buffer, 23 is an area histogram buffer, and 24 is a read pattern.

FIG. 3 shows an external view of this embodiment having the above configuration.

In the figure, the same components as in FIG. 1 are given the same numbers. 8
9 is an interface cable between the reader 1 and the host computer 3, and 9 is an interface cable between the printer 6 and the host computer 3.

The operation of this embodiment having the above configuration will be explained below with reference to the flowchart of FIG.

In FIG. 4, as in FIG. 10, the process of reading and recognizing a pattern indicated by P on a document set in the reader 1 will be described as an example.

First, in step S1, the CPU 50 activates the reader 1 via the reader interface 55, scans the surface of the document to be read, and reads image data on the surface of the document.

On the manuscript surface, for example, a circle mark is placed at the bottom of the OMR sheet shown in FIG. 9, and a type pattern is painted on the mark as shown in FIG. The OMR sheet is used for registering keywords in an electronic file system, inputting a telephone number for a facsimile, and setting modes such as the number of copies and reduction ratio of an image forming apparatus such as a copying machine.

If the format shown in FIG. 8 is fixed and a fixed pattern of characters is written on it, subsequent processing becomes easier. In addition, FIG. 8 shows standard patterns of degrees "A" to "Z" and 1 degrees to "o".

The basic pattern of the format in Figure 8 is 3 trees in the X direction, 3 trees in the y direction,
Direction 3 The character ``田'' composed of wooden strokes and diagonal 2
It is part of the shape that combines the stroke "x" on the other hand.

A case will be described below, taking as an example a case where one character, for example, °゛8to°, is read at the mark position on the document surface written in this manner.

The signal photoelectrically converted and read by the reader 1 in step S1 is sent to the reader interface 55 as shown in step S2, and converted into a binary pattern of 1°', "o" by the analog-to-digital converter built into the reader interface 55. is converted into a digital signal, and the converted digital signal is input to the CPU 50.

The CPU 50 sequentially stores the digital data thus manually input into the pattern buffer 21 of the RAM 57 . In the unimplemented example, the character pattern is divided into areas of 48 bits x 48 bits per character, and an example of storing read data in the pattern buffer 21 when reading "Aoo" is shown in FIG. , when the black density is detected, the data is "i".

In step S3, the CPtJ 50 takes a histogram of the number of strokes in the horizontal and vertical directions for each line. Specifically, as shown in FIG.
The histogram of the stroke distribution of the top line (in the direction) is °'1", the fourth line is °2", and the histogram of the stroke distribution of the leftmost line and the next line in the vertical direction (Y direction) is 1", the fifth line. is 2°'. Then, the histogram of the stroke distribution obtained in step S4 is RA
It is stored in the line histogram buffer 22 of M57.

In the next step S5, the reading pattern shown in FIG.
(2) Divide into each predetermined area shown in (A) 1 to 6 and AND. In each divided area, for example, the histogram of the stroke distribution for each line in the 61st (A) area 1 is as follows:
As shown in Figure 6 (B) 51, starting from the first line,
1, 1, 2.2.2'', and the area A becomes '2, 2, 3° 2.2'' from the first line as shown in 52.

Subsequently, in step S6, the minimum value of the histogram for each line within the predetermined area obtained earlier is obtained, and this value is used as the representative value of the area and is stored in the area histogram buffer 23 of the RAM 57.
Store in. In area 1, the minimum value of the histogram distribution is “1°”, and the area histogram buffer 23
This “1” is stored in . Similarly, in step s7, the maximum number of strokes that occur in the histogram distribution for each line within the predetermined region previously determined is determined and stored in the region histogram buffer 23 of the RAM 57. In area A, the maximum number of strokes that occur in the histogram distribution is "2",
This “2” is stored in the area histogram buffer 23.

Then, in step S8, a representative value for each area is determined, and the RAM
57 reading pattern 24. Here, the sixth
In regions 1 to 6 shown in Figure (A), the minimum value of the histogram distribution is taken as a representative value, and in regions A to D, the maximum number of generated strokes is taken as a representative value. This reading pattern 2
Figure 6 shows the storage status of representative values in all areas in 4 (
Shown in C).

In the following step SIO, standard characteristic pattern 5 of ROM51
The standard pattern stored in 1a is matched with the read pattern stored in read pattern 24.

As a result, if a pattern match is obtained in step 111, it is recognized as an input of the matched pattern in step S12, and the result is output. On the other hand, if a match cannot be obtained, the process advances to step S13, where an unrecognizable message is output and the process ends. Then, the next pattern reading process is executed again.

The m quasi-pattern of "'A" in the input standard feature pattern 51a is the pattern shown in FIG. 7, which matches the reading pattern shown in FIG. 6(C), and the human cover pattern in FIG. It is recognized that the amount of human power is

As explained above, according to this embodiment, the following effects can be considered in recognizing the character pattern shown in FIG. 5, for example.

(2) By using the maximum number of occurrences of the stroke distribution in a predetermined area as a representative value, this has the effect of eliminating readings of dust, etc., which are erroneous readings within the area. Therefore, even if the histogram changes slightly, such as when there is dust in the area and the histogram of the line becomes "3'" as shown in Figure 6 (B), the maximum number of occurrences in the stroke distribution can be used as the representative value. By doing so, this effect can be prevented and accurate character recognition becomes possible.

■Furthermore, since the amount of data to be matched is small, processing time is significantly reduced, making recognition possible by only matching a small amount of data: the pattern in Figure 6 (C) and the standard feature pattern shown in Figure 7. .

In this way, the drawbacks of the character recognition device in recognizing simple characters can be overcome, the processing time required for simple character recognition can be shortened, and character recognition can be performed at high speed and with high accuracy.

Furthermore, the diagnosis can be made by recognizing numbers or letters of the alphabet in a fixed pattern (printed type) at high speed and with high precision.

[Effect of the invention] As explained above, according to the present invention, in a very short time,
Moreover, accurate pattern recognition processing can be performed.

[Brief explanation of the drawing]

Fig. 1 is a block diagram of an embodiment according to the present invention, Fig. 2 is a detailed configuration diagram of the RAM shown in Fig. 1, Fig. 3 is an external view of this embodiment, and Fig. 4 is a pattern of this embodiment. Recognition control flowchart. FIG. 5 is a diagram showing an example of storing read patterns in the pattern buffer of this embodiment. FIGS. 6 (A) to (C) are putters according to this embodiment. FIG. Figure 8 is a diagram showing the storage pattern; Figure 8 is a diagram showing the standard cover pattern used in this example; Figure 9 is a diagram showing the OMR sheet used in this example; Figure 10 is a flowchart showing conventional pattern recognition processing. It is. In the figure, 1...reader, 2...optical disk, 3...
・Host computer, 4...Keyboard, 5...
CRT, 6...Printer, 7...Auto feeder,
50...CPU, 51...ROM,
51 a--Standard feature pattern storage area, 52-
... CRT interface, 53... Keyboard interface, 54... Optical disk interface, 5
5...Reader interface, 56...Printer interface, 57...RAM, 60...Bus. Patent applicant Canon Co., Ltd. Figure 2Φ

Claims (1)

[Claims] a reading step of optically reading pattern information on the reading surface;
a region dividing step of dividing the read pattern information into predetermined regions; a detection step of detecting a histogram of stroke distribution within a certain range for each region divided in the region dividing step; A pattern information recognition method comprising a recognition step of recognizing a maximum number of occurrences of a histogram of stroke distribution detected in the step as a representative value of the divided area.